Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity

• URL: http://arxiv.org/abs/2306.11626v4
• Date: Fri, 24 May 2024 05:51:18 GMT
• Title: Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
• Authors: Runyu Zhang, Yang Hu, Na Li,
• Abstract summary: This paper introduces a new formulation for risk-sensitive MDPs, which assesses risk in a slightly different manner compared to the classical Markov risk measure. We derive the policy gradient theorem for both problems, proving gradient domination and global convergence of the exact policy gradient method. We also propose a sample-based offline learning algorithm, namely the robust fitted-Z iteration (RFZI)
• Score: 7.57543767554282
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust Markov Decision Processes (MDPs) and risk-sensitive MDPs are both powerful tools for making decisions in the presence of uncertainties. Previous efforts have aimed to establish their connections, revealing equivalences in specific formulations. This paper introduces a new formulation for risk-sensitive MDPs, which assesses risk in a slightly different manner compared to the classical Markov risk measure (Ruszczy\'nski 2010), and establishes its equivalence with a class of soft robust MDP (RMDP) problems, including the standard RMDP as a special case. Leveraging this equivalence, we further derive the policy gradient theorem for both problems, proving gradient domination and global convergence of the exact policy gradient method under the tabular setting with direct parameterization. This forms a sharp contrast to the Markov risk measure, known to be potentially non-gradient-dominant (Huang et al. 2021). We also propose a sample-based offline learning algorithm, namely the robust fitted-Z iteration (RFZI), for a specific soft RMDP problem with a KL-divergence regularization term (or equivalently the risk-sensitive MDP with an entropy risk measure). We showcase its streamlined design and less stringent assumptions due to the equivalence and analyze its sample complexity

Related papers

• Certifiably Robust Policies for Uncertain Parametric Environments [57.2416302384766]
  We propose a framework based on parametric Markov decision processes (MDPs) with unknown distributions over parameters. We learn and analyse IMDPs for a set of unknown sample environments induced by parameters. We show that our approach produces tight bounds on a policy's performance with high confidence.
  arXiv  Detail & Related papers  (2024-08-06T10:48:15Z)
• Robust Risk-Sensitive Reinforcement Learning with Conditional Value-at-Risk [23.63388546004777]
  We analyze the robustness of CVaR-based risk-sensitive RL under Robust Markov Decision Processes. Motivated by the existence of decision-dependent uncertainty in real-world problems, we study problems with state-action-dependent ambiguity sets.
  arXiv  Detail & Related papers  (2024-05-02T20:28:49Z)
• Data-Adaptive Tradeoffs among Multiple Risks in Distribution-Free Prediction [55.77015419028725]
  We develop methods that permit valid control of risk when threshold and tradeoff parameters are chosen adaptively. Our methodology supports monotone and nearly-monotone risks, but otherwise makes no distributional assumptions.
  arXiv  Detail & Related papers  (2024-03-28T17:28:06Z)
• Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation [54.61816424792866]
  We introduce a general framework on Risk-Sensitive Distributional Reinforcement Learning (RS-DisRL), with static Lipschitz Risk Measures (LRM) and general function approximation. We design two innovative meta-algorithms: textttRS-DisRL-M, a model-based strategy for model-based function approximation, and textttRS-DisRL-V, a model-free approach for general value function approximation.
  arXiv  Detail & Related papers  (2024-02-28T08:43:18Z)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model [61.87673435273466]
  This paper investigates model robustness in reinforcement learning (RL) to reduce the sim-to-real gap in practice. We adopt the framework of distributionally robust Markov decision processes (RMDPs), aimed at learning a policy that optimize the worst-case performance when the deployed environment falls within a prescribed uncertainty set around the nominal MDP.
  arXiv  Detail & Related papers  (2023-05-26T02:32:03Z)
• Risk-Averse MDPs under Reward Ambiguity [9.929659318167731]
  We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity. A scalable first-order algorithm is designed to solve large-scale problems.
  arXiv  Detail & Related papers  (2023-01-03T11:06:30Z)
• RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk [28.811725782388688]
  We propose and analyze a new framework to jointly model the risk associated with uncertainties in finite-horizon and discounted infinite-horizon MDPs. We show that when the risk-aversion is defined using either EVaR or the entropic risk, the optimal policy in RASR can be computed efficiently using a new dynamic program formulation with a time-dependent risk level.
  arXiv  Detail & Related papers  (2022-09-09T00:34:58Z)
• Robust Entropy-regularized Markov Decision Processes [23.719568076996662]
  We study a robust version of the ER-MDP model, where the optimal policies are required to be robust. We show that essential properties that hold for the non-robust ER-MDP and robust unregularized MDP models also hold in our settings. We show how our framework and results can be integrated into different algorithmic schemes including value or (modified) policy.
  arXiv  Detail & Related papers  (2021-12-31T09:50:46Z)
• Cautious Reinforcement Learning via Distributional Risk in the Dual Domain [45.17200683056563]
  We study the estimation of risk-sensitive policies in reinforcement learning problems defined by a Markov Decision Process (MDPs) whose state and action spaces are countably finite. We propose a new definition of risk, which we call caution, as a penalty function added to the dual objective of the linear programming (LP) formulation of reinforcement learning.
  arXiv  Detail & Related papers  (2020-02-27T23:18:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.